Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Thyroid nodule ultrasonic image processing method based on cross-layer sparse cavity convolution

A technology of thyroid nodules and ultrasound images, applied in the field of ultrasound medical image information processing, can solve the problems of poor semantic extraction effect of ultrasound images and the like

Active Publication Date: 2020-08-14
HANGZHOU CHUANGYING HEALTH MANAGEMENT CO LTD
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The problem to be solved by the present invention is to provide a method for processing ultrasound images of thyroid nodules based on cross-layer sparse atrous convolution to solve the problem of poor semantic extraction effect of ultrasound images of thyroid nodules in existing deep learning networks

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Thyroid nodule ultrasonic image processing method based on cross-layer sparse cavity convolution
  • Thyroid nodule ultrasonic image processing method based on cross-layer sparse cavity convolution
  • Thyroid nodule ultrasonic image processing method based on cross-layer sparse cavity convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Reference attached figure 1 The method for processing ultrasound images of thyroid nodules based on cross-layer sparse atrous convolution shown in this embodiment includes the following steps:

[0054] In the first step, the original ultrasound images containing thyroid nodules are collected, and image training sets, verification sets, and test sets are established based on the collected original ultrasound images, and the thyroid nodules in each image collection are delineated.

[0055] Specifically, collect at least 15,000 images containing ultrasound images of thyroid nodules, and outline the shape of thyroid nodules in all images, among which at least 10,000 images are randomly selected as the training set, and at least 2,000 images of the remaining images are randomly selected as the verification set , and the remaining images randomly select at least 3000 images as the test set.

[0056] The second step is to establish an image preprocessing module to preprocess...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a thyroid nodule ultrasonic image processing method based on cross-layer sparse cavity convolution. A novel cross-layer cavity convolution network structure, a sparse constraint network, a separation sparse cavity convolution layer, and a loss function with adaptive weight adjustment and sparse constraint are established, the method overcomes the defects that an existing method is poor in thyroid nodule ultrasonic image nodule region semantic resolution capability, and semantic feature extraction of the nodule region is susceptible to interference of similar backgrounds, and solves the problem of poor extraction effect of a thyroid nodule ultrasonic image semantic probability heat map caused by limited receptive field expansion ability of a deep learning network ina forward propagation step.

Description

technical field [0001] The invention relates to the field of ultrasonic medical image information processing, in particular to a method for processing ultrasonic images of thyroid nodules based on cross-layer sparse atrous convolution. Background technique [0002] Thyroid nodules are clinically common lesions, most of which are benign nodules and some are malignant thyroid cancers. Ultrasound examination is the first choice for diagnosing thyroid nodules. How to use computer and image processing methods to accurately extract the semantic probability heat map of the nodule area in the ultrasound image is an important tool for thyroid nodule positioning, identification, segmentation, benign and malignant discrimination, and automatic nodule detection. Basis for applications such as grading. At present, the method based on deep convolutional neural network is an effective semantic probability heat map extraction method. This method first defines the deep learning network stru...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/62G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/62G06N3/08G06T2207/10132G06T2207/20076G06T2207/20081G06T2207/20084G06T2207/30096G06N3/047G06N3/048G06N3/045G06F18/2415G06F18/241
Inventor 姚劲草徐栋欧笛李伟杨琛汪丽菁王立平周玲燕朱乔丹张含芝张小
Owner HANGZHOU CHUANGYING HEALTH MANAGEMENT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com